TheBloke

/

Llama-2-70B-Chat-GGML

like 160

Hey Tom and Community,

Thank you so much for the hard work and effort you all put into these GGMLs! 👏👏👏

I’m currently on the lookout for an affordable GPU setup,
Specifically, I look for something that can comfortably handle the 8-bit version of 70B.
Do you have any recommendations?

Also, is there a website or forum where the community shares their GPU recommendations for different versions of LLM quantizations?

Thanks in advance for any advice or suggestions!